I came across this awesome project called Real Time Voice Cloning by Corentin Jemine and I wanted to give it a shot. I’m currently working on a Mac laptop, but I have access to a remote server with some GPUs that could easily run the toolbox, but I wanted an easy way to get everything setup. Docker would do the trick as far as getting it setup, and then through forwarding the X Window System via SSH, I could view and control the program locally as it ran remotely. Note that these steps should be more or less compatible with Linux or macOS, but maybe on Windows with the WSL. I’m not really sure, as I haven’t tested the following on anything except Linux and macOS.
Some variant of these instructions may allow the project to be ran with just a CPU, but I haven’t investigated that path, so you’re on your own there.
Follow the instructions here: https://github.com/NVIDIA/nvidia-docker. Note that you’ll need have installed the NVIDIA driver and Docker as well.
I’ll assume that you’re working from your home directory, and we’ll make a directory called
voice for our project to sit in and clone the GitHub repo:
cd ~ mkdir voice && cd voice git clone https://github.com/CorentinJ/Real-Time-Voice-Cloning.git
Next, download the pretrained models as described here: https://github.com/CorentinJ/Real-Time-Voice-Cloning/wiki/Pretrained-models. Note that you’re expected to merge the contents with the project root directory.
Create a new file called
Dockerfile and insert the following:
FROM pytorch/pytorch WORKDIR "/workspace" RUN apt-get clean \ && apt-get update \ && apt-get install -y ffmpeg libportaudio2 openssh-server python3-pyqt5 xauth \ && apt-get -y autoremove \ && mkdir /var/run/sshd \ && mkdir /root/.ssh \ && chmod 700 /root/.ssh \ && ssh-keygen -A \ && sed -i "s/^.*PasswordAuthentication.*$/PasswordAuthentication no/" /etc/ssh/sshd_config \ && sed -i "s/^.*X11Forwarding.*$/X11Forwarding yes/" /etc/ssh/sshd_config \ && sed -i "s/^.*X11UseLocalhost.*$/X11UseLocalhost no/" /etc/ssh/sshd_config \ && grep "^X11UseLocalhost" /etc/ssh/sshd_config || echo "X11UseLocalhost no" >> /etc/ssh/sshd_config ADD Real-Time-Voice-Cloning/requirements.txt /workspace/requirements.txt RUN pip install -r /workspace/requirements.txt RUN echo "<REPLACE THIS SENTENCE (INCLUDING ARROWS) WITH YOUR SSH PUBLIC KEY ON THE DOCKER HOST" \ >> /root/.ssh/authorized_keys RUN echo "export PATH=/opt/conda/bin:$PATH" >> /root/.profile ENTRYPOINT ["sh", "-c", "/usr/sbin/sshd && bash"] CMD ["bash"]
A rough summary of the above is that we:
- Use the pytorch docker image as our base image
- Update the image repos
- Install some dependencies
- ffmpeg as a backend for PortAudio
- libportaudio2 for audio manipulation (?)
- openssh-server to SSH into the container
- python3-pyqt5 for the QT bindings (installing via pip didn’t seem to work for me)
- xauth for X forwarding
- Set up the container to allow you to SSH in. This may not be secure, so I don’t advise using on any sort of public facing machine. Use at your discretion.
- Allow X forwarding with the SSH server within the container
- Add the repo’s
- Install those requirements
Action Required!!!: Insert your
SSH public keyso you can SSH into the container
- Add the right Python interpreter to the root user’s PATH
- Make sure the SSH server is running when the container starts
Note that if you plan on SSH’ing into the Docker host as well (like I did from my laptop to the docker host), you need to set
/etc/ssh/sshd_config on the docker host as well. Then reload and restart the SSH daemon (on Ubuntu this was
systemctl daemon-reload && systemctl restart sshd).
Add the following to your SSH config at
~/.ssh/config on the docker host (or create the file if it doesn’t exists):
Host voice Hostname localhost Port 2150 User root ForwardX11 yes ForwardX11Trusted yes
Run the following command to build the container:
docker build -t voice-base .
You should be able to run the following to test:
docker run -it --rm --init --runtime=nvidia \ --ipc=host --volume="$PWD:/workspace" \ -e NVIDIA_VISIBLE_DEVICES=0 -p 2150:22 \ --device /dev/snd voice-base nvidia-smi cd /workspace/Real-Time-Voice-Cloning python demo_cli.py exit
docker run -it --rm --init --runtime=nvidia \ --ipc=host --volume="$PWD:/workspace" \ -e NVIDIA_VISIBLE_DEVICES=0 -p 2150:22 \ --device /dev/snd voice-base
--device /dev/snd should allow the container to pass sound to the docker host, though I wasn’t able to get sound working going from
laptop->docker_host->container. I modified the
Real-Time-Voice-Cloning project to save the output audio as a WAV file instead of playing within the application, and then copied the file locally to listen to the results.
At this point, the container should be running and will occupy that terminal, so open up a new terminal shell
From the docker host, this is done with:
ssh -X voice
voice refers to the name of the host we configured in Step 6.
For connecting this from a macOS machine to the docker host, follow these steps that were found from Indiana University:
- Install XQuartz on your Mac, which is the official X server software for Mac
- Run Applications > Utilities > XQuartz.app
- Right click on the XQuartz icon in the dock and select Applications > Terminal. This should bring up a new xterm terminal windows.
From there, you will SSH into the docker host…:
ssh -X firstname.lastname@example.org
…and then SSH into the docker container:
ssh -X voice
Now that we have a terminal session that has X11 forwarding, we can navigate to the project directory and run the toolbox:
cd /workspace/Real-Time-Voice-Cloning python demo_cli.py
Note that you’ll need to provide audio in the form of the datasets discussed in the README of the project, or upload your own audio samples to the container and then browse to them within the toolbox application. This should be straightforward, since the project directory on the docker host is mounted within the container.
I realize that some of the methods used here probably aren’t best practice, but they worked for playing around with this great project over a holiday weekend and I hope they prove helpful to someone.